{"id":"https://openalex.org/W2803714261","doi":"https://doi.org/10.1109/icassp.2018.8462393","title":"ON the Use of Wavenet as a Statistical Vocoder","display_name":"ON the Use of Wavenet as a Statistical Vocoder","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2803714261","doi":"https://doi.org/10.1109/icassp.2018.8462393","mag":"2803714261"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015353805","display_name":"Nagaraj Adiga","orcid":"https://orcid.org/0000-0002-3438-567X"},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Nagaraj Adiga","raw_affiliation_strings":["Department of Computer Science, University of Crete"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Crete","institution_ids":["https://openalex.org/I142617266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049252564","display_name":"Vassilis Tsiaras","orcid":"https://orcid.org/0000-0002-6677-1946"},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Tsiaras","raw_affiliation_strings":["Department of Computer Science, University of Crete"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Crete","institution_ids":["https://openalex.org/I142617266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Department of Computer Science, University of Crete"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Crete","institution_ids":["https://openalex.org/I142617266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015353805"],"corresponding_institution_ids":["https://openalex.org/I142617266"],"apc_list":null,"apc_paid":null,"fwci":7.1074,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.97538459,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5674","last_page":"5678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7910170555114746},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7049093246459961},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6867757439613342},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6214452981948853},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5153736472129822},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4435260593891144},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.43929463624954224},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4153251349925995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32003259658813477},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.17393523454666138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910170555114746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7049093246459961},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6867757439613342},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6214452981948853},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5153736472129822},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4435260593891144},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.43929463624954224},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4153251349925995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32003259658813477},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.17393523454666138},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1966264494","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2111284386","https://openalex.org/W2120605154","https://openalex.org/W2120847449","https://openalex.org/W2129082420","https://openalex.org/W2141998673","https://openalex.org/W2150658333","https://openalex.org/W2156142001","https://openalex.org/W2164764235","https://openalex.org/W2394917751","https://openalex.org/W2519091744","https://openalex.org/W2598638573","https://openalex.org/W2604184139","https://openalex.org/W2619368999","https://openalex.org/W2746474733","https://openalex.org/W2747161606","https://openalex.org/W2749651610","https://openalex.org/W2963103134","https://openalex.org/W6603838645","https://openalex.org/W6712188339","https://openalex.org/W6735509194","https://openalex.org/W6740049204","https://openalex.org/W6743354777"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W2081919107","https://openalex.org/W1540615732"],"abstract_inverted_index":{"In":[0,16,140],"this":[1],"paper,":[2],"we":[3,40,101,143],"explore":[4],"the":[5,9,19,33,38,42,45,53,63,71,95,110,115,127,131,141,146,149,152,162,165],"possibility":[6],"of":[7,21,44,52,55,62,73,117,148,151,161],"using":[8,94],"WaveNet":[10,64,88,166],"architecture":[11,65,89],"as":[12,48,50,90,123,168,170],"a":[13,81,91],"statistical":[14],"vocoder.":[15],"that":[17,51],"case,":[18],"generation":[20],"speech":[22,92,97,167],"waveforms":[23],"is":[24],"locally":[25],"conditioned":[26],"only":[27],"by":[28,164],"acoustic":[29],"features.":[30],"Focusing":[31],"on":[32],"single":[34],"speaker":[35],"case":[36],"at":[37],"moment,":[39],"investigate":[41],"impact":[43,147],"local":[46,124],"conditions":[47],"well":[49,169],"amount":[54],"data":[56],"available":[57],"for":[58,134,157],"training.":[59],"Furthermore,":[60],"variations":[61],"are":[66],"considered":[67],"and":[68,105,120,137,159],"discussed":[69],"in":[70],"context":[72],"our":[74,78,174],"work.":[75],"We":[76],"compare":[77],"work":[79,84],"against":[80],"very":[82],"recent":[83],"which":[85],"also":[86,144],"used":[87,102],"vocoder":[93],"same":[96],"data.":[98,154],"More":[99],"specifically,":[100],"two":[103,106],"female":[104,138],"male":[107,136],"speakers":[108],"from":[109],"CMU-ARCTIC":[111],"database":[112],"to":[113,129],"contrast":[114],"use":[116],"cepstrum":[118],"coefficients":[119],"filter-bank":[121],"features":[122],"conditioners":[125],"with":[126],"goal":[128],"improve":[130],"overall":[132],"quality":[133,158],"both":[135],"speakers.":[139],"paper":[142],"discuss":[145],"size":[150],"training":[153],"Objective":[155],"metrics":[156],"intelligibility":[160],"generated":[163],"subjective":[171],"tests":[172],"support":[173],"suggestions.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":9}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}